The Event Crowd: A Novel Approach for Crowd-Enabled Event Processing

Abstract

Event processing systems involve the processing of high volume and variety data which has inherent uncertainties like incomplete event streams, imprecise event recognition etc. With the emergence of crowdsourcing platforms, the performance of event processing systems can be enhanced by including 'human-in-the-loop' to leverage their cognitive ability. The resulting crowd-sourced event processing can cater to the problem of event uncertainty and veracity by using humans to verify the results. This paper introduces the first hybrid crowd-enabled event processing engine. The paper proposes a list of five event crowd operators that are domain and language independent and can be used by any event processing framework. These operators encapsulate the complexities to deal with crowd workers and allow developers to define an event-crowd hybrid workflow. The operators are: Annotate, Rank, Verify, Rate, and Match. The paper presents a proof of concept of event crowd operators, schedulers, poolers, aggregators in an event processing system. The paper demonstrates the implementation of these operators and simulates the system with various performance metrics. The experimental evaluation shows that throughput of the system was 7.86 events per second with average latency of 7.16 seconds for 100 crowd workers. Finally, the paper concludes with avenues for future research in crowd-enabled event processing.